Reproduce “Large-Scale Benchmarking of Quantum Neural Network Configurations for Financial Time Series Forecasting” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jack Waller, Xing Liang, Dimitrios Makris, Rajagopal Nilavalan
The authors compare 1,368 quantum neural network configurations for forecasting daily GBP/USD rates, varying data encoding, gate patterns, qubits, layers, and training costs. Their best simulated individual run achieves test R² 0.98495, above the reported BiLSTM baselines. Tests on IQM Emerald show hardware noise degrades performance, limiting the finding to one exchange-rate series and tested circuits.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.